PyData London 2015

Smart Cars of Tomorrow

Transcript

1. IoT REALIZED CONNECTED CAR Ronert Obst Twitter: @ronert_obst
2. https://github.com/pivotal/IoT-ConnectedCar
3. B A C K T O T H E BEGINNING
4. REALLY COOL IoT PROJECT
5. COVERED BY AN NDA
7. CONNECTED CAR
8. PIECES ARE THE SAME
9. PREDICT THE DESTINATION
10. PREDICT THE RANGE
13. HOW DOES THIS WORK?
14. START IN THE CAR
15. ON BOARD DIAGNOSTICS OBD II
16. PHONE PROVIDES CONNECTIVITY 127.0.0.1:9000
17. { "vehicle_speed":103, "obd_standards":2, "intake_manifold_pressure":"", "accelerator_throttle_pos_e":14, "engine_load":89, "maf_airflow":33, "latitude":"32.897554", "vin":"1HGCM82633A004352", "bearing":"343.922580", "catalyst_temp":779, "relative_throttle_pos":12, "fuel_level_input":89, "fuel_system_status":[2,0], "accelerator_throttle_pos_d":29, "acceleration":"0.953", "throttle_position":21, "barometric_pressure":97, "control_module_voltage":13, "longitude":"-96.810236", "distance_with_mil_on":0, "coolant_temp":94, "intake_air_temp":34, "rpm":1593, "short_term_fuel":-2, "time_since_engine_start":4054, "absolute_throttle_pos_b":38, "long_term_fuel":3 }
18. TCP SOCKET OVER BLUETOOTH HTTP POST OVER CELLULAR
19. O N T H E SERVER
20. SPRING XD EXTREME DATA
21. SPRING Ingestion Orchestration Extraction Real-time Analytics
22. D I S T R I B U T E D RUNTIME
23. STREAMING BATCH &
25. http | filter | acmeenrich | shell | hdfs // Ingestion Stream Definitions
26. IoT-HTTP.shell > typeconversiontransformer | gemfire-server // Tap Definitions
27. TCP SOCKET OVER BLUETOOTH HTTP POST OVER CELLULAR
28. Spring XD HTTP transformers hdfs gemfire tap python hdfs GemFire REST API
29. Spring XD transformers hdfs gemfire tap python hdfs GemFire REST API PySpark
30. REALTIME DATA SCIENCE
31. 1PREDICT JOURNEY
32. HOW DOES IT WORK?
33. STORE SENSOR DATA
34. RECORDED JOURNEYS
35. OFFLINE BATCH TRAINING
36. J O U R N E Y CLUSTERS
37. INITIAL PREDICTION
38. DRIVING HOME TO WORK
39. DRIVING WORK TO HOME
40. ONLINE PREDICTION
41. 2PREDICT RANGE
42. … "Predictions": { "ClusterPredictions": { "0": { "EndLocation": [ 32.98525175453122, -96.70940837440399 ], "MPG_Journey": 25.60900810315203, "Probability": 0.63736 }, …
43. Pivotal HD Spring XD Realtime Evaluation Batch Training Data Persistence
45. R E A LT I M E DASHBOARD
46. GEMFIRE 1
47. REST 2
48. YOEMAN 3
49. ANGULARJS 4
50. SOLUTION AT SCALE
51. 100,000’s OF CLIENTS
52. MILLIONS OF MESSAGES
53. PER MINUTE OVER 100 GB
54. IoT ISSUES
55. COMPATIBILITY
56. CONNECTIVITY
57. SECURITY
58. LOOKING INTO THE FUTURE
60. AD D ITION AL USE CASES
61. F L EET MANAGEMENT
62. P RED ICTIV E MAINTENANCE
63. ACCID EN T ASSISTANCE
64. WE ARE HIRING • Data Scientists • Software Developers • Software Engineers • Product Managers • Platform Architects • Field Engineers pivotal.io/careers